The Biological Meaning of Radiomic Features

Radiology, Journal Year: 2021, Volume and Issue: 298(3), P. 505 - 516

Published: Jan. 5, 2021

Radiomic analysis offers a powerful tool for the extraction of clinically relevant information from radiologic imaging. Radiomics can be used to predict patient outcome through automated high-throughput feature extraction, using large training cohorts elucidate subtle relationships between image characteristics and disease status. However powerful, data-driven nature radiomics inherently no insight into biological underpinnings observed relationships. Early work was dominated by semantic, radiologist-defined features carried qualitative real-world meaning. Following rapid developments popularity machine learning approaches, field moved quickly toward agnostic analyses, resulting in increasingly sets. This trend took focus an increase predictive power further away understanding findings. Such disconnect predictor model meaning will limit broad clinical translation. Efforts reintroduce are gaining traction with distinct emerging approaches available, including genomic correlates, local microscopic pathologic textures, macroscopic histopathologic marker expression. These methods presented this review, their significance is discussed. The authors that following increasing pressure robust radiomics, validation become standard practice field, thus cementing role method decision making. © RSNA, 2021 An earlier incorrect version appeared online. article corrected on February 10, 2021.

Language: Английский

---

Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review

Annals of Oncology, Journal Year: 2023, Volume and Issue: 35(1), P. 29 - 65

Published: Oct. 23, 2023

Language: Английский

---

The artificial intelligence and machine learning in lung cancer immunotherapy

Journal of Hematology & Oncology, Journal Year: 2023, Volume and Issue: 16(1)

Published: May 24, 2023

Abstract Since the past decades, more lung cancer patients have been experiencing lasting benefits from immunotherapy. It is imperative to accurately and intelligently select appropriate for immunotherapy or predict efficacy. In recent years, machine learning (ML)-based artificial intelligence (AI) was developed in area of medical-industrial convergence. AI can help model medical information. A growing number studies combined radiology, pathology, genomics, proteomics data order expression levels programmed death-ligand 1 (PD-L1), tumor mutation burden (TMB) microenvironment (TME) likelihood side effects. Finally, with advancement ML, it believed that "digital biopsy" replace traditional single assessment method benefit clinical decision-making future. this review, applications PD-L1/TMB prediction, TME prediction are discussed.

Language: Английский

---

Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study

The Lancet Digital Health, Journal Year: 2023, Volume and Issue: 5(7), P. e404 - e420

Published: May 31, 2023

Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying biology. We aimed to investigate application deep learning on chest CT scans derive an imaging signature response immune checkpoint inhibitors evaluate its added value in clinical context.

Language: Английский

---

Radiogenomics: a key component of precision cancer medicine

British Journal of Cancer, Journal Year: 2023, Volume and Issue: 129(5), P. 741 - 753

Published: July 6, 2023

Language: Английский

---

Impact of [18F]FDG PET/CT Radiomics and Artificial Intelligence in Clinical Decision Making in Lung Cancer: Its Current Role

Seminars in Nuclear Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Lung cancer remains one of the most prevalent cancers globally and leading cause cancer-related deaths, accounting for nearly one-fifth all fatalities. Fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography ([18F]FDG PET/CT) plays a vital role in assessing lung managing disease progression. While traditional PET/CT imaging relies on qualitative analysis basic quantitative parameters, radiomics offers more advanced approach to analyzing tumor phenotypes. Recently, has gained attention its potential enhance prognostic diagnostic capabilities [18F]FDG various cancers. This review explores expanding PET/CT-based radiomics, particularly when integrated with artificial intelligence (AI), cancer, especially non-small cell (NSCLC). We how AI improve diagnostics, staging, subtype identification, molecular marker detection, which influence treatment decisions. Additionally, we address challenges clinical integration, such as protocol standardization, feature reproducibility, need extensive prospective studies. Ultimately, hold great promise enabling personalized effective treatments, potentially transforming management.

Language: Английский

---

Noninvasive imaging of the tumor immune microenvironment correlates with response to immunotherapy in gastric cancer

Nature Communications, Journal Year: 2022, Volume and Issue: 13(1)

Published: Aug. 30, 2022

Abstract The tumor immune microenvironment (TIME) is associated with prognosis and immunotherapy response. Here we develop validate a CT-based radiomics score (RS) using 2272 gastric cancer (GC) patients to investigate the relationship between imaging biomarker neutrophil-to-lymphocyte ratio (NLR) in TIME, including its correlation response advanced GC. RS achieves an AUC of 0.795–0.861 predicting NLR TIME. Notably, indistinguishable from IHC-derived status DFS OS each cohort (HR range: 1.694–3.394, P < 0.001). We find objective responses anti-PD-1 significantly higher low-RS group (60.9% 42.9%) than high-RS (8.1% 14.3%). noninvasive method evaluate may correlate anti PD-1 GC patients.

Language: Английский

---

Artificial intelligence and radiomics: fundamentals, applications, and challenges in immunotherapy

Journal for ImmunoTherapy of Cancer, Journal Year: 2022, Volume and Issue: 10(9), P. e005292 - e005292

Published: Sept. 1, 2022

Immunotherapy offers the potential for durable clinical benefit but calls into question association between tumor size and outcome that currently forms basis imaging-guided treatment. Artificial intelligence (AI) radiomics allow discovery of novel patterns in medical images can increase radiology’s role management patients with cancer, although methodological issues literature limit its application. Using keywords related to immunotherapy radiomics, we performed a review MEDLINE, CENTRAL, Embase from database inception through February 2022. We removed all duplicates, non-English language reports, abstracts, reviews, editorials, perspectives, case book chapters, non-relevant studies. From remaining articles, following information was extracted: publication information, sample size, primary site, imaging modality, secondary study objectives, data collection strategy (retrospective vs prospective, single center multicenter), radiomic signature validation strategy, performance, metrics calculation Radiomics Quality Score (RQS). identified 351 studies, which 87 were unique reports relevant our research question. The median (IQR) cohort sizes 101 (57–180). Primary stated goals model development prognostication (n=29, 33.3%), treatment response prediction (n=24, 27.6%), characterization phenotype (n=14, 16.1%) or immune environment (n=13, 14.9%). Most studies retrospective (n=75, 86.2%) recruited (n=57, 65.5%). For available on testing, most (n=54, 65.9%) used set better. Performance generally highest signatures predicting phenotype, as opposed overall prognosis. Out possible maximum 36 points, RQS 12 (10–16). While rapidly increasing number promising results offer proof concept AI could drive precision medicine approaches wide range indications, standardizing well optimizing quality rigor are necessary before these be translated practice.

Language: Английский

---

[18F]FDG-PET/CT Radiomics and Artificial Intelligence in Lung Cancer: Technical Aspects and Potential Clinical Applications

Seminars in Nuclear Medicine, Journal Year: 2022, Volume and Issue: 52(6), P. 759 - 780

Published: June 15, 2022

Lung cancer is the second most common and leading cause of cancer-related death worldwide. Molecular imaging using [18F]fluorodeoxyglucose Positron Emission Tomography and/or Computed ([18F]FDG-PET/CT) plays an essential role in diagnosis, evaluation response to treatment, prediction outcomes. The images are evaluated qualitative conventional quantitative indices. However, there far more information embedded images, which can be extracted by sophisticated algorithms. Recently, concept uncovering analyzing invisible data from medical called radiomics, gaining attention. Currently, [18F]FDG-PET/CT radiomics growingly lung discover if it enhances diagnostic performance or implication management cancer. In this review, we provide a short overview technical aspects, as they discussed different articles special issue. We mainly focus on [18F]FDG-PET/CT‐based artificial intelligence non-small cell cancer, impacting early detection, staging, tumor subtypes, biomarkers, patient's

Language: Английский

---

Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study

EBioMedicine, Journal Year: 2022, Volume and Issue: 86, P. 104364 - 104364

Published: Nov. 14, 2022

BackgroundThis study, based on multicentre cohorts, aims to utilize computed tomography (CT) images construct a deep learning model for predicting major pathological response (MPR) neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) and further explore the biological basis under its prediction.Methods274 patients undergoing curative surgery after NSCLC at 4 centres from January 2019 December 2021 were included divided into training cohort, an internal validation external cohort. ShuffleNetV2x05-based features of primary tumour CT scans within 2 weeks preceding administration employed develop score distinguishing MPR non-MPR. To reveal underlying score, genetic analysis was conducted 25 with RNA-sequencing data.FindingsMPR achieved 54.0% (n = 148) patients. The area curve (AUC) predict 0.73 (95% confidence interval [CI]: 0.58–0.86) 0.72 CI: 0.58–0.85) respectively. After integrating clinical characteristic combined satisfactory performance (AUC: 0.77, 95% 0.64–0.89) cohorts 0.75, 0.62–0.87). In exploration high associated downregulation pathways mediating proliferation promotion antitumour immune infiltration microenvironment.InterpretationThe proposed could effectively treated chemoimmunotherapy.FundingThis study supported by National Key Research Development Program China, China (2017YFA0205200); Natural Science Foundation (91959126, 82022036, 91959130, 81971776, 81771924, 6202790004, 81930053, 9195910169, 62176013, 8210071009); Beijing Foundation, (L182061); Strategic Priority Chinese Academy Sciences, (XDB38040200); (GJJSTD20170004, QYZDJ-SSW-JSC005); Shanghai Hospital Center, (SHDC2020CR3047B); Technology Commission Municipality, (21YF1438200).

Language: Английский

---